© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9188
    Prev
    Next
    INDEX
    Explanations

    like + description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    не
    1.53
    ز
    1.48
    ه
    1.43
    и
    1.24
    -\
    1.24
    ে
    1.21
     pore
    1.20
    მ
    1.19
    o
    1.17
    ン
    1.16
    POSITIVE LOGITS
    ínű
    1.32
    のが
    1.30
     infestation
    1.29
    ів
    1.26
    னர்
    1.25
     refroidissement
    1.22
    ின்
    1.21
    RAchievement
    1.21
    Victory
    1.21
     semelhante
    1.20
    Activations Density 0.152%

    No Known Activations